Video Matting

10 papers with code • 1 benchmarks • 4 datasets

Most implemented papers

MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition

ZHKKKe/MODNet 24 Nov 2020

MODNet is easy to be trained in an end-to-end manner.

Flow-based Video Segmentation for Human Head and Shoulders

kuangzijian/Flow-Based-Video-Matting 20 Apr 2021

Video segmentation for the human head and shoulders is essential in creating elegant media for videoconferencing and virtual reality applications.

Deep Video Matting via Spatio-Temporal Alignment and Aggregation

nowsyn/DVM CVPR 2021

Despite the significant progress made by deep learning in natural image matting, there has been so far no representative work on deep learning for video matting due to the inherent technical challenges in reasoning temporal domain and lack of large-scale video matting datasets.

Attention-guided Temporally Coherent Video Object Matting

yunkezhang/TCVOM 24 May 2021

Experimental results show that our method can generate high-quality alpha mattes for various videos featuring appearance change, occlusion, and fast motion.

Robust High-Resolution Video Matting with Temporal Guidance

PeterL1n/RobustVideoMatting 25 Aug 2021

We introduce a robust, real-time, high-resolution human video matting method that achieves new state-of-the-art performance.

One-Trimap Video Matting

hongje/otvm 27 Jul 2022

A key of OTVM is the joint modeling of trimap propagation and alpha prediction.

VMFormer: End-to-End Video Matting with Transformer

SHI-Labs/VMFormer 26 Aug 2022

In this paper, we propose VMFormer: a transformer-based end-to-end method for video matting.

Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity

nowsyn/sparsemat CVPR 2023

Instead, our method resorts to spatial and temporal sparsity for solving general UHR matting.

End-to-End Video Matting With Trimap Propagation

csvt32745/ftp-vm CVPR 2023

Although recent studies exploit video object segmentation methods to propagate the given trimaps, they suffer inconsistent results.

Video Instance Matting

shi-labs/vim 7 Nov 2023

To remedy this deficiency, we propose Video Instance Matting~(VIM), that is, estimating alpha mattes of each instance at each frame of a video sequence.